Hugging Face's logo

Sharukesh
/
en_pipeline

Token Classification
spaCy
English
Eval Results
Model card Files Community
en_pipeline
File size: 4,361 Bytes 
7fc57ed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
 
{
    "paths": {
        "train": "null",
        "dev": "null",
        "vectors": "null",
        "init_tok2vec": "null"
    },
    "system": {
        "gpu_allocator": "\"pytorch\"",
        "seed": "0"
    },
    "nlp": {
        "lang": "\"en\"",
        "pipeline": "[\"transformer\",\"ner\"]",
        "batch_size": "128",
        "disabled": "[]",
        "before_creation": "null",
        "after_creation": "null",
        "after_pipeline_creation": "null",
        "tokenizer": "{\"@tokenizers\":\"spacy.Tokenizer.v1\"}",
        "vectors": "{\"@vectors\":\"spacy.Vectors.v1\"}"
    },
    "components": {},
    "components.ner": {
        "factory": "\"ner\"",
        "incorrect_spans_key": "null",
        "moves": "null",
        "scorer": "{\"@scorers\":\"spacy.ner_scorer.v1\"}",
        "update_with_oracle_cut_size": "100"
    },
    "components.ner.model": {
        "@architectures": "\"spacy.TransitionBasedParser.v2\"",
        "state_type": "\"ner\"",
        "extra_state_tokens": "false",
        "hidden_width": "64",
        "maxout_pieces": "2",
        "use_upper": "false",
        "no": "null"
    },
    "components.ner.model.tok2vec": {
        "@architectures": "\"spacy-transformers.TransformerListener.v1\"",
        "grad_factor": "1.0",
        "pooling": "{\"@layers\":\"reduce_mean.v1\"}",
        "upstream": "\"*\""
    },
    "components.transformer": {
        "factory": "\"transformer\"",
        "max_batch_items": "4096",
        "set_extra_annotations": "{\"@annotation_setters\":\"spacy-transformers.null_annotation_setter.v1\"}"
    },
    "components.transformer.model": {
        "@architectures": "\"spacy-transformers.TransformerModel.v3\"",
        "name": "\"roberta-base\"",
        "mixed_precision": "false"
    },
    "components.transformer.model.get_spans": {
        "@span_getters": "\"spacy-transformers.strided_spans.v1\"",
        "window": "128",
        "stride": "96"
    },
    "components.transformer.model.grad_scaler_config": {},
    "components.transformer.model.tokenizer_config": {
        "use_fast": "true"
    },
    "components.transformer.model.transformer_config": {},
    "corpora": {},
    "corpora.dev": {
        "@readers": "\"spacy.Corpus.v1\"",
        "path": "${paths.dev}",
        "max_length": "0",
        "gold_preproc": "false",
        "limit": "0",
        "augmenter": "null"
    },
    "corpora.train": {
        "@readers": "\"spacy.Corpus.v1\"",
        "path": "${paths.train}",
        "max_length": "0",
        "gold_preproc": "false",
        "limit": "0",
        "augmenter": "null"
    },
    "training": {
        "accumulate_gradient": "3",
        "dev_corpus": "\"corpora.dev\"",
        "train_corpus": "\"corpora.train\"",
        "seed": "${system.seed}",
        "gpu_allocator": "${system.gpu_allocator}",
        "dropout": "0.1",
        "patience": "1600",
        "max_epochs": "0",
        "max_steps": "20000",
        "eval_frequency": "200",
        "frozen_components": "[]",
        "annotating_components": "[]",
        "before_to_disk": "null",
        "before_update": "null"
    },
    "training.batcher": {
        "@batchers": "\"spacy.batch_by_padded.v1\"",
        "discard_oversize": "true",
        "size": "2000",
        "buffer": "256",
        "get_length": "null"
    },
    "training.logger": {
        "@loggers": "\"spacy.ConsoleLogger.v1\"",
        "progress_bar": "false"
    },
    "training.optimizer": {
        "@optimizers": "\"Adam.v1\"",
        "beta1": "0.9",
        "beta2": "0.999",
        "l2_is_weight_decay": "true",
        "l2": "0.01",
        "grad_clip": "1.0",
        "use_averages": "false",
        "eps": "0.00000001"
    },
    "training.optimizer.learn_rate": {
        "@schedules": "\"warmup_linear.v1\"",
        "warmup_steps": "250",
        "total_steps": "20000",
        "initial_rate": "0.00005"
    },
    "training.score_weights": {
        "ents_f": "1.0",
        "ents_p": "0.0",
        "ents_r": "0.0",
        "ents_per_type": "null"
    },
    "pretraining": {},
    "initialize": {
        "vectors": "${paths.vectors}",
        "init_tok2vec": "${paths.init_tok2vec}",
        "vocab_data": "null",
        "lookups": "null",
        "before_init": "null",
        "after_init": "null"
    },
    "initialize.components": {},
    "initialize.tokenizer": {}
}